基于分块直方图帧差变化率的镜头分割算法研究

A Shot Segmentation Algorithm Based on Partitioned Histogram Change Rate of Frame Difference

在介绍了目前主流的镜头分割算法后,文章提出一种基于分块直方图帧差变化率的镜头分割算法。该算法主要分为两部分:突变检测和渐变检测。首先利用图像的HSV分块直方图特征计算相邻帧帧差,将其与自适应的突变阈值比较从而确定突变镜头的位置。然后利用突变分割得到的视频段进行镜头渐变的检测。对每一个视频段利用相邻帧帧差变化率的规律来判定渐变位置。实验结果表明,该方法具有较高的准确率,并且易于实现。

After introducing the current mainstream video shot segmentation algorithms, an adaptive shot segmentation algorithm based on partitioned histogram change rate of frame difference is proposed. The algorithm is mainly divided into two parts： abrupt change detection and gradual change detection. Firstly using the HSV partitioned histogram to calculate the frame difference of adjacent frames. Compare it with the adaptive threshold of abrupt change, and then determine the position of the abrupt change shot. Then using video segments, which is from abrupt change cut, to detect the gradual changes of video shot. Using regular pattern of neighbor frame difference change rate to determine the position of gradual change. Experimental results show that the method in this paper has high accuracy, and it is easy to implement.